GCG benchmarks

mathog at seqaxp.bio.caltech.edu mathog at seqaxp.bio.caltech.edu
Thu May 4 17:32:13 EST 1995

In article <Pine.ULT.3.91.950502125817.24275A-100000 at resunix.ri.sickkids.on.ca>, Jimi Xenidis <jimix at sickkids.on.ca> writes:
>We are in the process of purchasing a Unix machine specifically for 
>running the GCG software.  Does anyone know of any banchmarks and/or 
>reviews of how different machines run GCG.

GCG doesn't come with benchmarks, but Phylip does.  When I ran those on our
2100 A500MP (190 Mhz AXP) about 6 months ago many of programs became IO
limited. (Ie, it was taking more time to load the program and write out the
results than to do the calculations.)  This was with OpenVMS 6.1,  If you
want Unix instead of OpenVMS, the Digital Unix speed should be nearly
identical on the same hardware.  Oh yeah, you can buy 275 Mhz AXPs now,
which will be about 50% faster. 

All that being said, probably the standard benchmarks (SPEC, linpack, etc.)
will be adequate indicators of the speed you will see.  At least, on a 
lightly loaded system.


David Mathog
mathog at seqvax.bio.caltech.edu
Manager, sequence analysis facility, biology division, Caltech 

More information about the Info-gcg mailing list

Send comments to us at biosci-help [At] net.bio.net